Related papers: Improving Accented Speech Recognition using Data A…

Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority…

Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS (EAT) model that incorporates two main features: 1) The ASR$\rightarrow$TTS direction is equipped with a language model reward to…

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…

Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet current Text-To-Speech (TTS) systems primarily model…

We propose UnitSpeech, a speaker-adaptive speech synthesis method that fine-tunes a diffusion-based text-to-speech (TTS) model using minimal untranscribed data. To achieve this, we use the self-supervised unit representation as a pseudo…

The scarcity of speaker-annotated far-field speech presents a significant challenge in developing high-performance far-field speaker verification (SV) systems. While data augmentation using large-scale near-field speech has been a common…

In this paper we study the impact of augmenting spoken language corpora with domain-specific synthetic samples for the purpose of training a speech recognition system. Using both a conventional neural TTS system and a zero-shot one with…

In this paper we investigate cross-lingual Text-To-Speech (TTS) synthesis through the lens of adapters, in the context of lightweight TTS systems. In particular, we compare the tasks of unseen speaker and language adaptation with the goal…

Direct speech-to-speech translation (S2ST) is among the most challenging problems in the translation paradigm due to the significant scarcity of S2ST data. While effort has been made to increase the data size from unlabeled speech by…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve…

Adapting generic speech recognition models to specific individuals is a challenging problem due to the scarcity of personalized data. Recent works have proposed boosting the amount of training data using personalized text-to-speech…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…

Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates…

Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT)…

Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied degrees of success. In this paper, we propose to jointly learn representations during pretraining from two different modalities: speech and text. The…

Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the…